derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
176 lines
6.3 KiB
LLVM
176 lines
6.3 KiB
LLVM
; Test strict vector maximum on z14.
|
|
;
|
|
; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z14 | FileCheck %s
|
|
|
|
declare double @llvm.experimental.constrained.maxnum.f64(double, double, metadata)
|
|
declare <2 x double> @llvm.experimental.constrained.maxnum.v2f64(<2 x double>, <2 x double>, metadata)
|
|
declare double @llvm.experimental.constrained.maximum.f64(double, double, metadata)
|
|
declare <2 x double> @llvm.experimental.constrained.maximum.v2f64(<2 x double>, <2 x double>, metadata)
|
|
|
|
declare float @llvm.experimental.constrained.maxnum.f32(float, float, metadata)
|
|
declare <4 x float> @llvm.experimental.constrained.maxnum.v4f32(<4 x float>, <4 x float>, metadata)
|
|
declare float @llvm.experimental.constrained.maximum.f32(float, float, metadata)
|
|
declare <4 x float> @llvm.experimental.constrained.maximum.v4f32(<4 x float>, <4 x float>, metadata)
|
|
|
|
declare half @llvm.experimental.constrained.maxnum.f16(half, half, metadata)
|
|
declare half @llvm.experimental.constrained.maximum.f16(half, half, metadata)
|
|
|
|
declare fp128 @llvm.experimental.constrained.maxnum.f128(fp128, fp128, metadata)
|
|
declare fp128 @llvm.experimental.constrained.maximum.f128(fp128, fp128, metadata)
|
|
|
|
; Test the f64 maxnum intrinsic.
|
|
define double @f1(double %dummy, double %val1, double %val2) #0 {
|
|
; CHECK-LABEL: f1:
|
|
; CHECK: wfmaxdb %f0, %f2, %f4, 4
|
|
; CHECK: br %r14
|
|
%ret = call double @llvm.experimental.constrained.maxnum.f64(
|
|
double %val1, double %val2,
|
|
metadata !"fpexcept.strict") #0
|
|
ret double %ret
|
|
}
|
|
|
|
; Test the v2f64 maxnum intrinsic.
|
|
define <2 x double> @f2(<2 x double> %dummy, <2 x double> %val1,
|
|
<2 x double> %val2) #0 {
|
|
; CHECK-LABEL: f2:
|
|
; CHECK: vfmaxdb %v24, %v26, %v28, 4
|
|
; CHECK: br %r14
|
|
%ret = call <2 x double> @llvm.experimental.constrained.maxnum.v2f64(
|
|
<2 x double> %val1, <2 x double> %val2,
|
|
metadata !"fpexcept.strict") #0
|
|
ret <2 x double> %ret
|
|
}
|
|
|
|
; Test the f16 maxnum intrinsic.
|
|
define half @f3_half(half %dummy, half %val1, half %val2) #0 {
|
|
; CHECK-LABEL: f3_half:
|
|
; CHECK: brasl %r14, __extendhfsf2@PLT
|
|
; CHECK: brasl %r14, __extendhfsf2@PLT
|
|
; CHECK: wfmaxsb %f0, %f0, %f9, 4
|
|
; CHECK: brasl %r14, __truncsfhf2@PLT
|
|
; CHECK: br %r14
|
|
%ret = call half @llvm.experimental.constrained.maxnum.f16(
|
|
half %val1, half %val2,
|
|
metadata !"fpexcept.strict") #0
|
|
ret half %ret
|
|
}
|
|
|
|
; Test the f32 maxnum intrinsic.
|
|
define float @f3(float %dummy, float %val1, float %val2) #0 {
|
|
; CHECK-LABEL: f3:
|
|
; CHECK: wfmaxsb %f0, %f2, %f4, 4
|
|
; CHECK: br %r14
|
|
%ret = call float @llvm.experimental.constrained.maxnum.f32(
|
|
float %val1, float %val2,
|
|
metadata !"fpexcept.strict") #0
|
|
ret float %ret
|
|
}
|
|
|
|
; Test the v4f32 maxnum intrinsic.
|
|
define <4 x float> @f4(<4 x float> %dummy, <4 x float> %val1,
|
|
<4 x float> %val2) #0 {
|
|
; CHECK-LABEL: f4:
|
|
; CHECK: vfmaxsb %v24, %v26, %v28, 4
|
|
; CHECK: br %r14
|
|
%ret = call <4 x float> @llvm.experimental.constrained.maxnum.v4f32(
|
|
<4 x float> %val1, <4 x float> %val2,
|
|
metadata !"fpexcept.strict") #0
|
|
ret <4 x float> %ret
|
|
}
|
|
|
|
; Test the f128 maxnum intrinsic.
|
|
define void @f5(ptr %ptr1, ptr %ptr2, ptr %dst) #0 {
|
|
; CHECK-LABEL: f5:
|
|
; CHECK-DAG: vl [[REG1:%v[0-9]+]], 0(%r2)
|
|
; CHECK-DAG: vl [[REG2:%v[0-9]+]], 0(%r3)
|
|
; CHECK: wfmaxxb [[RES:%v[0-9]+]], [[REG1]], [[REG2]], 4
|
|
; CHECK: vst [[RES]], 0(%r4)
|
|
; CHECK: br %r14
|
|
%val1 = load fp128, ptr %ptr1
|
|
%val2 = load fp128, ptr %ptr2
|
|
%res = call fp128 @llvm.experimental.constrained.maxnum.f128(
|
|
fp128 %val1, fp128 %val2,
|
|
metadata !"fpexcept.strict") #0
|
|
store fp128 %res, ptr %dst
|
|
ret void
|
|
}
|
|
|
|
; Test the f64 maximum intrinsic.
|
|
define double @f11(double %dummy, double %val1, double %val2) #0 {
|
|
; CHECK-LABEL: f11:
|
|
; CHECK: wfmaxdb %f0, %f2, %f4, 1
|
|
; CHECK: br %r14
|
|
%ret = call double @llvm.experimental.constrained.maximum.f64(
|
|
double %val1, double %val2,
|
|
metadata !"fpexcept.strict") #0
|
|
ret double %ret
|
|
}
|
|
|
|
; Test the v2f64 maximum intrinsic.
|
|
define <2 x double> @f12(<2 x double> %dummy, <2 x double> %val1,
|
|
<2 x double> %val2) #0 {
|
|
; CHECK-LABEL: f12:
|
|
; CHECK: vfmaxdb %v24, %v26, %v28, 1
|
|
; CHECK: br %r14
|
|
%ret = call <2 x double> @llvm.experimental.constrained.maximum.v2f64(
|
|
<2 x double> %val1, <2 x double> %val2,
|
|
metadata !"fpexcept.strict") #0
|
|
ret <2 x double> %ret
|
|
}
|
|
|
|
; Test the f16 maximum intrinsic.
|
|
define half @f13_half(half %dummy, half %val1, half %val2) #0 {
|
|
; CHECK-LABEL: f13_half:
|
|
; CHECK: brasl %r14, __extendhfsf2@PLT
|
|
; CHECK: brasl %r14, __extendhfsf2@PLT
|
|
; CHECK: wfmaxsb %f0, %f0, %f9, 1
|
|
; CHECK: brasl %r14, __truncsfhf2@PLT
|
|
; CHECK: br %r14
|
|
%ret = call half @llvm.experimental.constrained.maximum.f16(
|
|
half %val1, half %val2,
|
|
metadata !"fpexcept.strict") #0
|
|
ret half %ret
|
|
}
|
|
|
|
; Test the f32 maximum intrinsic.
|
|
define float @f13(float %dummy, float %val1, float %val2) #0 {
|
|
; CHECK-LABEL: f13:
|
|
; CHECK: wfmaxsb %f0, %f2, %f4, 1
|
|
; CHECK: br %r14
|
|
%ret = call float @llvm.experimental.constrained.maximum.f32(
|
|
float %val1, float %val2,
|
|
metadata !"fpexcept.strict") #0
|
|
ret float %ret
|
|
}
|
|
|
|
; Test the v4f32 maximum intrinsic.
|
|
define <4 x float> @f14(<4 x float> %dummy, <4 x float> %val1,
|
|
<4 x float> %val2) #0 {
|
|
; CHECK-LABEL: f14:
|
|
; CHECK: vfmaxsb %v24, %v26, %v28, 1
|
|
; CHECK: br %r14
|
|
%ret = call <4 x float> @llvm.experimental.constrained.maximum.v4f32(
|
|
<4 x float> %val1, <4 x float> %val2,
|
|
metadata !"fpexcept.strict") #0
|
|
ret <4 x float> %ret
|
|
}
|
|
|
|
; Test the f128 maximum intrinsic.
|
|
define void @f15(ptr %ptr1, ptr %ptr2, ptr %dst) #0 {
|
|
; CHECK-LABEL: f15:
|
|
; CHECK-DAG: vl [[REG1:%v[0-9]+]], 0(%r2)
|
|
; CHECK-DAG: vl [[REG2:%v[0-9]+]], 0(%r3)
|
|
; CHECK: wfmaxxb [[RES:%v[0-9]+]], [[REG1]], [[REG2]], 1
|
|
; CHECK: vst [[RES]], 0(%r4)
|
|
; CHECK: br %r14
|
|
%val1 = load fp128, ptr %ptr1
|
|
%val2 = load fp128, ptr %ptr2
|
|
%res = call fp128 @llvm.experimental.constrained.maximum.f128(
|
|
fp128 %val1, fp128 %val2,
|
|
metadata !"fpexcept.strict") #0
|
|
store fp128 %res, ptr %dst
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { strictfp }
|